Systemic Analysis of Fall Accidents Caused by Worker Inattention at Construction Sites: An Integrated Approach using HFACS and LLM

DaHye Kim; SangUk Han

doi:10.13161/kibim.2024.14.4.023

All Issue

2024 Vol.14, Issue 4 Preview Page Next Page

Research Article

Systemic Analysis of Fall Accidents Caused by Worker Inattention at Construction Sites: An Integrated Approach using HFACS and LLM 작업자 부주의로 인한 건설 현장 떨어짐 사고의 시스템적 분석: HFACS와 LLM의 결합 방법론

31 December 2024. pp. 23-34

PDF XML

Abstract

Accident investigation records have shown that human error is a major cause of accidents in construction. It has been pointed out that instead of blaming the victim who made the error, management approaches and strategies are required to better prevent the occurrence of similar incidents. However, accident records often include only proximal causes rather than root causes that may help determine future preventive actions from a management perspective. This paper thus explores a systemic approach to infer root causes of accidents from the accident descriptions, which include rich information on how they occurred. Specifically, the proposed approach integrates the human factors analysis and classification system with a large language model to analyze 1,816 fall accident cases extracted from publicly available accident reports. Using prompt engineering, we designed the Claude 3.5 Sonnet model for the classification system, achieving a valid rate of 99.34%. Results revealed distinct patterns in unsafe acts at different working heights. For example, as height increased from less than 2 m to 10 m, skill-based errors decreased from 65% to 28%, while routine violations increased from 12% to 42%. However, preconditions of unsafe acts, inadequate supervision, and organizational influences were consistent regardless of height. By leveraging a large language to analyze large-scale data, this research thus uncovered evolving patterns of unsafe acts with increasing working height, suggesting height-specific safety strategies for the prevention of fall accidents in practice.

Keywords

Construction Safety

Human Error

Worker Inattention

Systemic Analysis

Large Language Model

키워드

건설 안전

인적 오류

작업자 부주의

시스템적 분석

대규모 언어 모델

References

Anthropic (2024). Claude 3.5 Sonnet, https://www.anthropic.com/news/claude-3-5-sonnet (Jul. 19. 2024).

Chokor, A., Naganathan, H., Chong, W. K., El Asmar, M. (2016). Analyzing Arizona OSHA Injury Reports Using Unsupervised Machine Learning, Procedia Engineering, 145, pp. 1588-1593.

10.1016/j.proeng.2016.04.200

Garrett, J. W., Teizer, J. (2009). Human Factors Analysis Classification System Relating to Human Error Awareness Taxonomy in Construction Safety, Journal of Construction Engineering and Management, 135(8), pp. 754-763.

10.1061/(ASCE)CO.1943-7862.0000034

Jalali, M., Dehghan, H., Habibi, E., Khakzad, N. (2023). Application of "Human Factor Analysis and Classification System" (HFACS) Model to the Prevention of Medical Errors and Adverse Events: A Systematic Review, International Journal of Preventive Medicine, 14, 127.

10.4103/ijpvm.ijpvm_123_2238264566PMC10803676

Jia, Q., Fu, G., Xie, X., Xue, Y., Hu, S. (2024). Enhancing Accident Cause Analysis through Text Classification and Accident Causation Theory: A Case Study of Coal Mine Gas Explosion Accidents, Process Safety and Environmental Protection, 185, pp. 989-1002.

10.1016/j.psep.2024.03.066

Kang, S., Cho, S., Yun, S., Kim, S. (2021). Semantic Network Analysis Using Construction Accident Cases to Understand Workers' Unsafe Acts, International Journal of Environmental Research and Public Health, 18(23), 12660.

10.3390/ijerph18231266034886388PMC8656935

Kaptan, M., Sarıalioğlu, S., Uğurlu, Ö., Wang, J. (2021). The Evolution of the HFACS Method Used in Analysis of Marine Accidents: A Review, International Journal of Industrial Ergonomics, 86, 103225.

10.1016/j.ergon.2021.103225

Khan, N., Nadeau, S., Xuan-Tan, P., Boton, C. (2024). Exploring Associations between Accident Types and Activities in Construction Using Natural Language Processing, Automation in Construction, 164, 105457.

10.1016/j.autcon.2024.105457

Korea Authority of Land & Infrastructure Safety (KALIS). (2023). An Investigation and Analysis of International Best Practices for Reducing Construction Accident Rates (건설사고 재해율 저감을 위한 해외 선진사례 조사 및 분석 연구), https://dl.nanet.go.kr/SearchDetailView.do?cn=MONO12023000022017 (Oct. 24. 2024).

Kumi, L., Jeong, J., Jeong, J. (2024). Data-Driven Automatic Classification Model for Construction Accident Cases Using Natural Language Processing with Hyperparameter Tuning, Automation in Construction, 164, 105458.

10.1016/j.autcon.2024.105458

Lavie, N. (1995). Perceptual Load as a Necessary Condition for Selective Attention, Journal of Experimental Psychology: Human Perception and Performance, 21(3), 451.

10.1037//0096-1523.21.3.4517790827

Li, J., Wu, C. (2023). Deep Learning and Text Mining: Classifying and Extracting Key Information from Construction Accident Narratives, Applied Sciences, 13(19), 10599.

10.3390/app131910599

Lim, J. G., Choi, J. D., Kang, T. W., Kim, B. C., Ham, D. H. (2020). HFACS-K: A Method for Analyzing Human Error- Related Accidents in Manufacturing Systems: Development and Case Study, Journal of the Korean Society of Safety, 35(4), pp. 64-73.

Ma, Z., Chen, Z.-S. (2024). Mining Construction Accident Reports via Unsupervised NLP and Accimap for Systemic Risk Analysis, Automation in Construction, 161, 105343.

10.1016/j.autcon.2024.105343

Pan, X., Zhong, B., Wang, Y., Shen, L. (2022). Identification of Accident-Injury Type and Bodypart Factors from Construction Accident Reports: A Graph-based Deep Learning Framework, Advanced Engineering Informatics, 54, 101752.

10.1016/j.aei.2022.101752

Rafindadi, A. D., Napiah, M., Othman, I., Mikić, M., Haruna, A., Alarifi, H., Al-Ashmori, Y. Y. (2022). Analysis of the Causes and Preventive Measures of Fatal Fall-Related Accidents in the Construction Industry, Ain Shams Engineering Journal, 13(4), 101712.

10.1016/j.asej.2022.101712

Read, G. J., Shorrock, S., Walker, G. H., Salmon, P. M. (2021). State of Science: Evolving Perspectives on 'Human Error', Ergonomics, 64(9), pp. 1091-1114.

10.1080/00140139.2021.195361534243698

Shappell, S. A., Wiegmann, D. A. (2000). The Human Factors Analysis and Classification System - HFACS, No. DOT/ FAA/AM-00/7, United States, Office of Aviation Medicine.

Smetana, M., Salles de Salles, L., Sukharev, I., Khazanovich, L. (2024). Highway Construction Safety Analysis Using Large Language Models, Applied Sciences, 14(4), 1352.

10.3390/app14041352

Tixier, A. J. P., Hallowell, M. R., Rajagopalan, B., Bowman, D. (2016). Automated Content Analysis for Construction Safety: A Natural Language Processing System to Extract Precursors and Outcomes from Unstructured Injury Reports, Automation in Construction, 62, pp. 45-56.

10.1016/j.autcon.2015.11.001

Wang, J., Zou, P. X., Li, P. P. (2016). Critical Factors and Paths Influencing Construction Workers' Safety Risk Tolerances, Accident Analysis & Prevention, 93, pp. 267-279.

10.1016/j.aap.2015.11.02726775077

Wang, Y., Cui, J., Zhang, Y., Geng, X. (2024). Study and Action Plan on the Key Factors Influencing Unsafe Behaviors by Construction Workers, Buildings, 14(7), 1973.

10.3390/buildings14071973

Wei, J., Wang, X., Schuurmans, D., Bosma, M., Ichter, B., Xia, F., Chi, E. H., Le, Q. V., Zhou, D. (2022). Chain-of-Thought Prompting Elicits Reasoning in Large Language Models, Advances in Neural Information Processing Systems, 35, 24824-24837.

Wong, L., Wang, Y., Law, T., Lo, C. T. (2016). Association of Root Causes in Fatal Fall-from-Height Construction Accidents in Hong Kong, Journal of Construction Engineering and Management, 142(7), 04016018.

10.1061/(ASCE)CO.1943-7862.0001098

Woolley, M., Goode, N., Salmon, P., Read, G. (2020). Who is Responsible for Construction Safety in Australia? A STAMP Analysis, Safety Science, 132, 104984.

10.1016/j.ssci.2020.104984

Ye, G., Tan, Q., Gong, X., Xiang, Q., Wang, Y., Liu, Q. (2018). Improved HFACS on Human Factors of Construction Accidents: A China Perspective, Advances in Civil Engineering, 2018(1), 4398345.

10.1155/2018/4398345

Yoo, B., Kim, J., Park, S., Ahn, C. R., Oh, T. (2024). Harnessing Generative Pre-Trained Transformers for Construction Accident Prediction with Saliency Visualization, Applied Sciences, 14(2), 664.

10.3390/app14020664

Yoon, Y. S., Ham, D. H., Yoon, W. C. (2017). A New Approach to Analysing Human-Related Accidents by Combined Use of HFACS and Activity Theory-Based Method, Cognition, Technology & Work, 19, pp, 759-783.

10.1007/s10111-017-0433-3

Zhang, F., Fleyeh, H., Wang, X., Lu, M. (2019). Construction Site Accident Analysis using Text Mining and Natural Language Processing Techniques, Automation in Construction, 99, pp. 238-248.

10.1016/j.autcon.2018.12.016

Zhang, X., Peng, B., Tian, Y., Zhou, J., Jin, L., Song, L., Mi, H., Meng, H. (2024). Self-Alignment for Factuality: Mitigating Hallucinations in LLMs via Self-Evaluation. arXiv preprint arXiv:2402.09267.

10.18653/v1/2024.acl-long.107

Information

Publisher :Journal of KIBIM
Publisher(Ko) :한국BIM학회
Journal Title :Journal of KIBIM
Journal Title(Ko) :한국BIM학회논문집
Volume : 14
No :4
Pages :23-34
Received Date : 2024-09-27; 2024-10-29
Accepted Date : 2024-10-30
DOI :https://doi.org/10.13161/kibim.2024.14.4.023

Journal of KIBIM ISSN:2288-1697(Print) 2288-1697(Online) 한국BIM학회논문집

All Issue